Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ball

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ($('#
    -0.07
     exposure
    -0.06
     attendees
    -0.06
     Marriage
    -0.06
    scheduler
    -0.06
    .Points
    -0.06
     producto
    -0.06
    (am
    -0.06
    stitution
    -0.06
    (dataset
    -0.06
    POSITIVE LOGITS
     �
    0.08
     needed
    0.07
    ball
    0.06
    跳
    0.06
    ceph
    0.06
    needs
    0.06
     کار
    0.06
     senses
    0.06
     busty
    0.06
    订
    0.06
    Act Density 0.002%

    No Known Activations